Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2843 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.4589. Min Range: -5.4589

Max Act: 5.4589. Min Act: -0.0000

Data Index: 589476 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 5.4589. Min Range: -5.4589

Max Act: 5.2304. Min Act: -0.0000

Data Index: 975150 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 5.4589. Min Range: -5.4589

Max Act: 2.2512. Min Act: -0.0000

Data Index: 626485 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 5.4589. Min Range: -5.4589

Max Act: 2.0219. Min Act: -0.0000

Data Index: 1424154 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 5.4589. Min Range: -5.4589

Max Act: 2.3549. Min Act: -0.0000

Data Index: 1195429 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1600405 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.7976. Min Act: -0.0000

Data Index: 308909 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1469055 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.5225. Min Act: -0.0000

Data Index: 1531959 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1415727 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1494165 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.8225. Min Act: -0.0000

Data Index: 1311938 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.2090. Min Act: -0.0000

Data Index: 572826 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 5.4589. Min Range: -5.4589

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1745700 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 5.4589. Min Range: -5.4589

Max Act: 0.5405. Min Act: -0.0000

Data Index: 502038 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1350083 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.4888. Min Act: -0.0000

Data Index: 534879 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 5.4589. Min Range: -5.4589

Max Act: 1.1516. Min Act: -0.0000

Data Index: 107122 (The Pile)

Max Activating Token Index: 767

Text #18

Max Range: 5.4589. Min Range: -5.4589

Max Act: 0.9587. Min Act: -0.0000

Data Index: 416876 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 5.4589. Min Range: -5.4589

Max Act: 0.9222. Min Act: -0.0000

Data Index: 591362 (The Pile)

Max Activating Token Index: 198